Update app.py

app.py

@@ -1,51 +1,44 @@
-import os
 import gradio as gr
-import joblib
+import pandas as pd
 import torch
+import joblib
 from transformers import AutoTokenizer, AutoModelForSequenceClassification
 
-# ✅ 1. Define your model directory
-model_repo = os.path.abspath("./campaign_bert_model/campaign_bert_model")
+# ✅ Fixed: Use relative path (NOT absolute)
+model_repo = "campaign_bert_model/campaign_bert_model"
 
-# ✅ 2. Load tokenizer and model
+# ✅ Load tokenizer and model
 tokenizer = AutoTokenizer.from_pretrained(model_repo, use_fast=False)
 model = AutoModelForSequenceClassification.from_pretrained(model_repo)
 
-# ✅ 3. Load label encoder
+# ✅ Load label encoder
 label_encoder = joblib.load("campaign_bert_model/label_encoder.pkl")
 
-# ✅ 4. Define prediction function
-def predict(client_interest, sentiment):
-    try:
-        text = f"{client_interest} Sentiment: {sentiment}"
-        inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True)
-        with torch.no_grad():
-            outputs = model(**inputs)
-            probs = torch.nn.functional.softmax(outputs.logits, dim=1)
-            pred_idx = torch.argmax(probs, dim=1).item()
-            pred_label = label_encoder.inverse_transform([pred_idx])[0]
-            confidence = probs[0][pred_idx].item()
-
-        return f"""
-### 🎯 Predicted Template ID:
-**🟢 {pred_label}**
-
-### 📊 Confidence:
-`{confidence * 100:.2f}%`
-"""
-    except Exception as e:
-        return f"❌ Error: {str(e)}"
-
-# ✅ 5. Gradio UI
-with gr.Blocks() as demo:
-    gr.Markdown("# 🧠 Campaign Personalizer AI\nPredict best template ID based on interest & sentiment.")
+# ✅ Prediction function
+def predict_template(client_interest, sentiment):
+    text = f"{client_interest} Sentiment: {sentiment}"
+    inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True)
+    
+    with torch.no_grad():
+        outputs = model(**inputs)
+        prediction = torch.argmax(outputs.logits, dim=1).item()
+    
+    predicted_template = label_encoder.inverse_transform([prediction])[0]
+    
+    return f"🎯 Predicted Template: **{predicted_template}**"
+
+# ✅ Gradio UI
+with gr.Blocks(title="Campaign Personalizer") as demo:
+    gr.Markdown("# 🧠 Campaign Personalizer\nPredict the best template based on client interest and sentiment.")
+    
     with gr.Row():
-        client_interest = gr.Textbox(label="📝 Client Interest", placeholder="e.g., Interested in term insurance")
-        sentiment = gr.Textbox(label="😊 Sentiment", placeholder="e.g., positive / negative / neutral")
-    submit = gr.Button("🔍 Predict Template")
+        client_input = gr.Textbox(label="Client Interest")
+        sentiment_input = gr.Textbox(label="Sentiment (e.g., Positive, Neutral, Negative)")
+
     output = gr.Markdown()
-    submit.click(fn=predict, inputs=[client_interest, sentiment], outputs=output)
 
-# ✅ 6. Launch the app
-if __name__ == "__main__":
-    demo.launch()
+    predict_button = gr.Button("🔍 Predict Template")
+    predict_button.click(fn=predict_template, inputs=[client_input, sentiment_input], outputs=output)
+
+# ✅ Launch
+demo.launch()